Dust event is one of the atmospheric events of the world arid and semi-arid areas that had a significant increase in recent years and negative effects in different parts. In this study used MODIS data to identify and select the best algorithm for dust detection. For this purpose, three dust events of South West of Iran detected in 2012 using five different algorithms of dust detection including Ackerman BTD, Miller, dust index, TIIDI and DUST RGB methods, and methods compared. Studies show that methods of Ackerman BTD, Dust index, and Miller need to threshold regulation for each dust event; for this reason, the suitable threshold was determined for each dust event using histogram method and dust identified. In addition, TIIDI method could separate dust phenomenon from other complications on the surface of the earth but as well could not identify dust on water. In DUST RGB method as well dust identified from other complication. In addition results of images classification and accuracy assessment showed that in all three dust events, DUST RGB method has maximum total accuracy among of other methods. Therefore, based on the results of matrix error and accuracy assessment, DUST RGB method was chosen as the best algorithm for dust detection.

Introduction: A dust aerosol index (DAI) algorithm based on measurements in deep blue (412 nm), blue (440 nm), and shortwave IR (2130 nm) wavelengths using Moderate Resolution Imaging Spectroradiometer (MODIS) observations has been developed. Measurements made in the short-wavelength segment, such as the deep blue or ultraviolet section, are well-detectable in the desert area. Using short-range waves, the visual retention of fine-grained mass data, especially in desert areas, was carefully monitored. The western and southwestern Iran are always exposed to dusty systems due to its vicinity to the deserts of neighboring countries. With regard to the fact that most of the spectral indices proposed for the identification of dust have been tested and implemented based on satellite indicators for desert areas, these indicators and their related thresholds for complex topography areas need more accurate analyses. Therefore, in the western and southwestern Iran, which are mountainous with a diverse vegetation, it is necessary to test and evaluate dust detection methods. Material and methods: The study area included Khuzestan, Ilam and Kermanshah provinces, which is about 107307 square kilometers. In this study, MODIS L1B data from the Aqua satellite was used for dusty days on May 18 and June 25, 2013 and 2015. Before performing spectral calculations on various products, the data of this sensor was preprocessed, which included geometric correction of images, mask cloud and water masks with ENVI and the conversion tool module. After preprocessing (georges, separating the study area, and water mask, and cloud cover) the satellite data, the retrieved spatial radiance of TOA was normalized using satellite data considering the sun's conditions for each wavelength. Results and discussion: In general, it was found that all AOD maps generated from the direct method showed a very good spatial distribution of the local aerosol pattern compared to other methods. As expected, the retrieved AOD map from the L1B spectrum showed that the spatial distribution of the local AOD was very clear. The DAI index algorithm simulates the high-spectral dependence of the atmosphere in the blue wavelength for different surface and atmosphere conditions with a fully tested copy of the radiation-transfer code of-6 S, which is a trusted tool for measuring particle pumping over the oceans, different surfaces of the earth, and clouds. Conclusion: Unlike some of the dust detection algorithms that are carried out using measurements in the infrared thermal band, the advantage of this algorithm to detect dust is the use of spectral scattering, reflection of the surface, and absorption of dust in the air. The advantage of using measurments in the blue wavelength (410 to 490 nm) is to recover the optical properties of the aerosol.

Geographical location and proximity to countries such as Saudi Arabia, Pakistan and Afghanistan as well as desert conditions and poor vegetation cover, weather instability and high winds have caused dust storms in different parts of Hormozgan province. This phenomenon is nowadays recognized as one of the environmental challenges in southern Iran. In order to study the dust phenomena in Hormozgan province, were first analyzed the dust data of twelve synoptic stations in the region between 2000 and 2018 Ackerman’s model, Normalized Difference Dust Index (NDDI), Thermal-infrared Dust Index (TDI) and Thermal Infrared Integrated Dust Index (TIIDI) were four Algorithm methods for dust source and plume identification using MODIS data MODIS Level 1B and MODIS Level 2 aerosol data to delineate and compares. Results showed that Qeshm station with 2762 days had the most and Minab station with 356 days had the least frequency of dust occurrence in the province. Also, 2007, 2008 and 2003 have the highest occurrence among the studied years. According to the survey data from 35716 days associated with dust phenomenon, 84% of dust events in the stations were locally originated (code 07) and 16% were of external source (06). The results also showed that the most occurrence of dust occurred in May, April and July, and the least occurrence of dust occurred in November, December and October. The results are shows all of the techniques except NDDI were successful in detecting dust plumes, but the most effective algorithm for plumes identification varied from event to event. In addition, TDI is the best algorithm comparing 3 evidence and eastern regions of Hormozgan, Jazmoorian area, Sistan and Baluchestan, and the western part of Afghanistan and Pakistan and south of Saudi Arabia are most important for dust source in Hormozgan Province.

The increasing popularity of the Internet has led to the dramatic growth of e-commerce. However, such activities have significant security challenges, mainly due to cyber fraud and identity theft. Therefore, checking the legitimacy of visited web pages is a very important task to secure the identity of customers and prevent phishing attacks. The use of machine learning methods, and deep learning is widely recognized as a promising solution. Research is full of studies that use machine learning and deep learning methods to detect website phishing. However, their findings depend on the data set and are far from generalizable. The two main reasons for the lack of generalization are impractical replication and lack of appropriate benchmark data sets for fair evaluation of systems. Furthermore, phishing methods are constantly evolving and the proposed models do not keep up with the rapid changes. In this article, we review the methods of identifying phishing sites from legal sites and finally reach the final conclusion.

Iran has always been exposed to dust storms because of its climate, geographical location and proximity with the neighbor’s desert such as Iraq, Syria and the Saudi. Hence, detection of dust phenomenon is a critical issue facing our world. In this research, the dust storms which occurred in Eilam and Khuzestan provinces during 2005 to 2012 were detected using multispectral technique and applied criteria in global models were customized for the study area. For this purpose, a decision tree algorithm is utilized for distinguishing cloud and dust and then the dust from ground surface is separated using the same reflectance behavior. First, appropriate training data for three classes of cloud, dust over dark and bright surfaces and clear sky is selected. Secondly, the reflectance behavior of pixels in the mentioned classes is analyzed. In the next step the best bands for the detection of dust pixels are chosen and the improved decision tree is recommended for the study area. Finally, the accuracy of the proposed algorithm is evaluated and compared with the previous algorithms using criteria such as visibility and weather codes from the meteorological data of the study area. The results show if the improved method is used the accuracy would increase. Eventually, if the Normalized Difference Dust Index (NDDI) Indicators and Ln (b1) are used for dust detection over bright surface, the accuracy will be 58 percent. Moreover, for dark surfaces the accuracy of 53 percent is achieved using the NDDI and BTD (BT20-BT31).

Today, search engines are the gateway to the web. With the increasing popularity of the web, the efforts to exploit it for commercial, social, and political purposes have also increased, making it difficult for search engines to distinguish good content from spam. The concept of web spam was first introduced in 1996 and quickly became recognized as one of the key challenges for the search engine industry. The phenomenon of spam occurs primarily because a significant portion of web page visits comes from search engines, and users tend to check the first search results. The goal of identifying spam pages is to ensure that these pages cannot achieve high rankings using deceptive strategies. Our effort is to provide an effective method for identifying spam pages, thereby reducing the presence of spam in the top search results. In this article, two methods for combating web spam are proposed. The first method, called XGspam, identifies spam pages based on the XGBoost learning algorithm with an accuracy of 94.27%. The second method, named XGSspam, offers a solution to the challenge of imbalanced web data by combining the SMOTE oversampling algorithm with the XGBoost classification model, achieving an accuracy of 95.44% in identifying spam pages.